In contrast to the previous FCN that generates one score map, our FCN is designed to compute a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances.
Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors.
Ranked #16 on Image Classification on Kuzushiji-MNIST
Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
Ranked #1 on Image Classification on CUB-200-2011 (Top 1 Accuracy metric)
In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals.
Ranked #5 on Real-Time Object Detection on PASCAL VOC 2007
We discover that aside from deep feature maps, a deep and convolutional per-region classifier is of particular importance for object detection, whereas latest superior image classification models (such as ResNets and GoogLeNets) do not directly lead to good detection accuracy without using such a per-region classifier.
In this work, we study rectifier neural networks for image classification from two aspects.
This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale.
Ranked #1 on Image Classification on ImageNet (Hardware Burden metric)
The locality principle guides us to learn a set of highly discriminative local binary features for each facial landmark independently.